Fault detection method and device based on rule matching, equipment and storage medium

Abstract

The invention relates to the technical field of rule matching, and discloses a fault detection method, device and equipment based on rule matching and a storage medium, and the method comprises the steps: obtaining sound information and vibration information corresponding to a vehicle when a fault signal of the vehicle is detected; obtaining vehicle image information of the vehicle from a preset vehicle image database, wherein the preset vehicle image database stores a global image of the vehicle collected in real time; determining a target fault component corresponding to the vehicle based on the sound information, the vibration information and the vehicle image information; and determining component information of the target fault component, and matching and determining target fault information corresponding to the vehicle based on the component information and a rule tree in the rule engine. According to the invention, the target fault information of the vehicle is determined based on the fault information of the target fault component of the vehicle and the rule tree in the rule engine, and the technical problem of low vehicle fault detection efficiency caused by long reasoning time of fault detection based on rule matching in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of rule matching, and in particular to a fault detection method, device, equipment and storage medium based on rule matching. Background Art

[0002] As cars gradually develop towards intelligence and electrification, the faults generated by cars and the amount of data involved are also gradually increasing. At this time, vehicle fault detection can be performed through vehicle data to ensure vehicle driving safety. In existing solutions, vehicle fault-related data can be matched with pre-established fault rules in the vehicle system to achieve vehicle fault detection. However, due to the large scale of fault rules in vehicles, the reasoning time of fault detection based on rule matching is long, which leads to low efficiency of vehicle fault detection.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a rule-matching-based fault detection method, device, equipment and storage medium, aiming to solve the technical problem in the prior art that the reasoning time of rule-matching-based fault detection is long, resulting in low vehicle fault detection efficiency.

[0005] To achieve the above object, the present invention provides a fault detection method based on rule matching, and the fault detection method based on rule matching includes:

[0006] When a fault signal of a vehicle is detected, obtaining sound information and vibration information corresponding to the vehicle;

[0007] Acquiring vehicle image information of the vehicle from a preset vehicle image database, wherein the preset vehicle image database stores a global image of the vehicle collected in real time;

[0008] determining a target faulty component corresponding to the vehicle based on the sound information, the vibration information and the vehicle image information;

[0009] Component information of the target fault component is determined, and target fault information corresponding to the vehicle is determined based on the component information and a rule tree match in a rule engine.

[0010] Optionally, the step of determining a target faulty component corresponding to the vehicle based on the sound information, the vibration information and the vehicle image information includes:

[0011] determining an abnormal area of ​​the vehicle according to the sound information and the vibration information;

[0012] Extracting target image information corresponding to the abnormal area from the vehicle image information;

[0013] A target faulty component corresponding to the vehicle is determined based on the target image information.

[0014] Optionally, the step of determining a target faulty component corresponding to the vehicle based on the target image information includes:

[0015] Extracting component feature information corresponding to the abnormal area from the target image information;

[0016] Acquire standard component feature information corresponding to all components in the abnormal area;

[0017] comparing the component characteristic information with the standard component characteristic information;

[0018] Determining the matching degree between the component feature information and the standard component feature information according to the comparison result;

[0019] A target faulty component corresponding to the vehicle is determined from the abnormal area according to the matching degree.

[0020] Optionally, the step of determining target fault information corresponding to the vehicle based on the component information and rule tree matching in the rule engine includes:

[0021] Performing semantic recognition on the component information to extract component names and component additional information from the component information;

[0022] Searching for a target rule tree with the component name as a root node from a rule tree of a rule engine;

[0023] The component additional information is matched with the target rule tree to determine target fault information corresponding to the vehicle.

[0024] Optionally, the step of matching the component additional information with the target rule tree to determine target fault information corresponding to the vehicle includes:

[0025] Determine the component operation state and target fault phenomenon corresponding to the target faulty component according to the component additional information;

[0026] Sequentially matching the component operation state and the target fault phenomenon with the first subnode and the second subnode in the target rule tree;

[0027] The target fault information corresponding to the vehicle is determined according to the matching result.

[0028] Optionally, the step of determining target fault information corresponding to the vehicle according to the matching result includes:

[0029] Obtaining phenomenon weight information corresponding to the target fault phenomenon;

[0030] Determine the fault category corresponding to the target faulty component according to the matching result and the phenomenon weight information;

[0031] Determine a fault cause corresponding to the fault category, and determine target fault information corresponding to the vehicle according to the fault cause.

[0032] Optionally, after the step of determining the target fault information corresponding to the vehicle based on the component information and the rule tree matching in the rule engine, the method further includes:

[0033] Determining a fault influencing factor according to the target fault information;

[0034] Determine whether the fault influencing factor is an environmental factor;

[0035] If so, obtain the current environment information and determine the fault resolution strategy based on the current environment information;

[0036] Fault resolution is performed on the vehicle according to the fault resolution strategy.

[0037] In addition, to achieve the above object, the present invention also proposes a fault detection device based on rule matching, the device comprising:

[0038] An information acquisition module, used to acquire sound information and vibration information corresponding to the vehicle when a fault signal of the vehicle is detected;

[0039] The information acquisition module is further used to acquire vehicle image information of the vehicle from a preset vehicle image database, wherein the preset vehicle image database stores a global image of the vehicle collected in real time;

[0040] a faulty component determination module, configured to determine a target faulty component corresponding to the vehicle based on the sound information, the vibration information and the vehicle image information;

[0041] A fault detection module is used to determine component information of the target faulty component, and determine target fault information corresponding to the vehicle based on the component information and rule tree matching in a rule engine.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also proposes a rule-matching-based fault detection device, which includes: a memory, a processor, and a rule-matching-based fault detection program stored in the memory and executable on the processor, and the rule-matching-based fault detection program is configured to implement the steps of the rule-matching-based fault detection method described above.

[0043] In addition, to achieve the above objectives, the present invention also proposes a storage medium, on which a rule-matching-based fault detection program is stored. When the rule-matching-based fault detection program is executed by a processor, the steps of the rule-matching-based fault detection method described above are implemented.

[0044] The present invention discloses that when a fault signal of a vehicle is detected, sound information and vibration information corresponding to the vehicle are obtained; vehicle image information of the vehicle is obtained from a preset vehicle image database, in which a global image of the vehicle collected in real time is stored; a target fault component corresponding to the vehicle is determined based on the sound information, vibration information and vehicle image information; component information of the target fault component is determined, and the target fault information corresponding to the vehicle is determined based on the component information and rule tree matching in a rule engine; compared with the prior art in which the fault-related data of the vehicle is matched with the fault rules pre-established in the vehicle system to realize fault detection of the vehicle, the present invention determines the target fault component of the vehicle based on the sound information, vibration information and vehicle image information of the vehicle, and determines the target fault information of the vehicle based on the fault information of the target fault component and rule tree matching in the rule engine, thereby solving the technical problem in the prior art that the reasoning time of fault detection based on rule matching is long, resulting in low efficiency of vehicle fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A schematic diagram of the structure of a fault detection device based on rule matching in a hardware operating environment involved in an embodiment of the present invention;

[0046] Figure 2 It is a flow chart of a first embodiment of a fault detection method based on rule matching of the present invention;

[0047] Figure 3 A schematic diagram of a rule tree in the first embodiment of the fault detection method based on rule matching of the present invention;

[0048] Figure 4 It is a flow chart of a second embodiment of a fault detection method based on rule matching of the present invention;

[0049] Figure 5 It is a flow chart of a third embodiment of a fault detection method based on rule matching of the present invention;

[0050] Figure 6 It is a structural block diagram of the first embodiment of the fault detection device based on rule matching of the present invention.

[0051] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0052] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0053] Reference Figure 1 , Figure 1 The present invention is a schematic diagram of a fault detection device structure based on rule matching in a hardware operating environment according to an embodiment of the present invention.

[0054] like Figure 1 As shown, the fault detection device based on rule matching may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0055] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the fault detection device based on rule matching, and may include more or less components than those shown in the figure, or combine certain components, or arrange the components differently.

[0056] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a fault detection program based on rule matching.

[0057] exist Figure 1In the rule-matching-based fault detection device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the rule-matching-based fault detection device of the present invention can be set in the rule-matching-based fault detection device, and the rule-matching-based fault detection device calls the rule-matching-based fault detection program stored in the memory 1005 through the processor 1001, and executes the rule-matching-based fault detection method provided by the embodiment of the present invention.

[0058] The embodiment of the present invention provides a fault detection method based on rule matching. Figure 2 , Figure 2 It is a flowchart of the first embodiment of the fault detection method based on rule matching of the present invention.

[0059] In this embodiment, the fault detection method based on rule matching includes the following steps:

[0060] Step S10: When a fault signal of a vehicle is detected, the sound information and vibration information corresponding to the vehicle are obtained.

[0061] It should be noted that the execution subject of the method of this embodiment can be a rule-matching-based fault detection device that realizes vehicle fault detection through rule matching, or other rule-matching-based fault detection systems that can realize the same or similar functions and include the rule-matching-based fault detection device. Here, the rule-matching-based fault detection method provided in this embodiment and the following embodiments is specifically described with the rule-matching-based fault detection system (hereinafter referred to as the system).

[0062] It should be noted that the above fault signal may be a signal triggered when a vehicle fails. In practical applications, when a vehicle fails, a corresponding fault signal may be triggered, and the system may detect the fault signal triggered by the vehicle.

[0063] It should be understood that the above-mentioned sound information may be the sound emitted by all running components in the vehicle, wherein the sound information in this embodiment may include the sound emitted by the vehicle's external components (such as the vehicle chassis, engine, etc.) and the vehicle's internal components (such as the air-conditioning outlet, vehicle audio, etc.) during the vehicle's driving, and this embodiment does not limit this. At the same time, the sound information in this embodiment may include but is not limited to sound intensity, sound frequency, etc.

[0064] It is understandable that the above vibration information may be the vibration emitted by all running components in the vehicle, wherein the sound information in this embodiment may include the vibration emitted by the external components of the vehicle (such as the vehicle chassis, engine, etc.) and the internal components of the vehicle (such as the air outlet of the air conditioner, the car audio, etc.) during the driving process of the vehicle, and this embodiment does not limit this. At the same time, the vibration information in this embodiment may include but is not limited to the vibration amplitude, vibration frequency, etc.

[0065] In practical applications, sound collection devices and vibration monitoring devices can be installed in advance at appropriate locations inside and outside the vehicle, so that when the vehicle is running, the sound collection devices and vibration monitoring devices can collect sound information and vibration information of all running parts of the vehicle in real time. Then, when the subsequent system detects a fault signal of the vehicle, it can directly obtain the sound information and vibration information of all running parts, thereby improving the fault detection efficiency.

[0066] Step S20: Acquire vehicle image information of the vehicle from a preset vehicle image database, wherein the preset vehicle image database stores a global image of the vehicle collected in real time.

[0067] It should be noted that the above-mentioned preset vehicle image database may be a database storing a global image of a vehicle, wherein the global image of the vehicle may include a global image of the interior of the vehicle, a global image of the top of the vehicle, and a global image of the bottom of the vehicle, etc. This embodiment does not impose any restrictions on this.

[0068] It should be understood that the above-mentioned vehicle image information may be image information of various operating components in the vehicle, wherein the operating components may include all operating components inside the vehicle, on the top of the vehicle and on the bottom of the vehicle, and this embodiment does not impose any limitation on this.

[0069] In this embodiment, the system can collect image information of all running parts in the vehicle in real time through the image acquisition device, and store all collected image information in a preset vehicle image database, so that when the vehicle fails later, the pre-collected image information can be directly obtained from the preset vehicle image database.

[0070] Step S30: determining a target faulty component corresponding to the vehicle based on the sound information, the vibration information and the vehicle image information.

[0071] It should be noted that the target faulty component mentioned above may be a faulty component in the vehicle.

[0072] In actual applications, the system can first preliminarily determine which area's components are faulty based on the vehicle's sound and vibration information, and then further determine which specific component in the area is faulty through the vehicle's image information, thereby determining the target faulty component corresponding to the vehicle.

[0073] Step S40: Determine component information of the target fault component, and determine target fault information corresponding to the vehicle based on the component information and rule tree matching in a rule engine.

[0074] It is understandable that the above-mentioned component information may be relevant information of the target faulty component, such as: the name, operating status, fault phenomenon, etc. of the target faulty component, which is not limited in this embodiment.

[0075] It should be noted that the rule engine is a component embedded in the application. Most rule engines support rule implementation in simple scripting languages ​​and embedded development in general development languages. The rule engine separates business decisions from application code and uses predefined semantic modules to write business decisions. The application triggers the rule engine by submitting data or objects to the rule engine, which calls the corresponding rules and triggers the corresponding operations.

[0076] It should be noted that the rule tree may be a pre-built tree storing the corresponding relationship between the faulty component, the running state of the component and the fault phenomenon. Figure 3 , Figure 3 FIG. 1 is a schematic diagram of a rule tree in the first embodiment of the fault detection method based on rule matching of the present invention. Figure 3 As shown, the rule tree may store the corresponding relationship between the components running in the vehicle and their corresponding running states, and the fault phenomena that may exist in the running states.

[0077] It can be understood that the above-mentioned target fault information may be information such as the reasons that may cause the target fault component to have the fault phenomenon in the corresponding operating state.

[0078] In actual applications, if the target fault component is found to be the engine of the vehicle according to the sound information, vibration information and image information corresponding to the vehicle, the operating state of the engine (including the operable state and the stopped operating state) can be determined at this time. If the engine is in the operable state, the fault phenomenon of the engine at this time can be determined, such as: the engine can rotate but not ignite, the engine automatically shuts down during driving, and the engine can start but immediately shuts down. Then, according to the target fault component, the operating state of the component and the fault phenomenon, the target fault information of the fault component in this operating state can be matched from the rule tree in the rule engine, thereby realizing the fault detection of the vehicle.

[0079] Furthermore, in order to perform fault processing after detecting a vehicle fault and ensure driving safety, after step S40, the method also includes: determining fault influencing factors based on the target fault information; judging whether there are environmental factors in the fault influencing factors; if so, obtaining current environmental information and determining a fault resolution strategy based on the current environmental information; and performing fault processing on the vehicle according to the fault resolution strategy.

[0080] It should be noted that the above-mentioned fault influencing factors may be factors that cause vehicle faults, such as road factors, environmental factors, etc., which are not limited in this embodiment. Among them, environmental factors may be factors such as humidity and temperature in the environment when the vehicle is driving.

[0081] It should be noted that the above current environmental information may be information such as temperature and humidity in the current environment.

[0082] It is understandable that the above fault resolution strategy may be a strategy for resolving the current fault of the vehicle.

[0083] In actual applications, the system can determine the cause of the vehicle's current fault based on the vehicle's target fault information, and determine the influencing factors of the fault based on the cause of the current fault. At this time, it can be determined whether the influencing factors include environmental factors, that is, whether the current environment of the vehicle has an impact on the vehicle's current fault. If so, the fault resolution strategy can be determined based on the current environmental information of the vehicle, and the vehicle is fault-handled according to the fault resolution strategy. Specifically, if the component of the vehicle that has a fault this time is a tire, and the fault phenomenon is insufficient tire pressure, the vehicle's tire pressure may be insufficient due to the low temperature of the vehicle. Therefore, it can be determined that the influencing factors causing the vehicle's current fault include environmental factors. At this time, the environmental information of the vehicle's current environment can be obtained, that is, the temperature, humidity and other information of the vehicle's current environment can be obtained, and the solution strategy for this fault can be determined based on this information, such as driving to an area with a higher temperature, inflating the tires, etc., so as to handle the vehicle's fault according to the fault resolution strategy and ensure the vehicle's driving safety.

[0084] The present embodiment discloses that when a fault signal of a vehicle is detected, the sound information and vibration information corresponding to the vehicle are obtained; the vehicle image information of the vehicle is obtained from a preset vehicle image database, and the preset vehicle image database stores a global image of the vehicle collected in real time; the target fault component corresponding to the vehicle is determined based on the sound information, vibration information and vehicle image information; the component information of the target fault component is determined, and the target fault information corresponding to the vehicle is determined based on the component information and the rule tree matching in the rule engine; compared with the prior art in which the fault-related data of the vehicle is matched with the fault rules pre-established in the vehicle system to realize the fault detection of the vehicle, since the present embodiment determines the target fault component of the vehicle based on the sound information, vibration information and vehicle image information of the vehicle, and determines the target fault information of the vehicle based on the fault information of the target fault component and the rule tree matching in the rule engine, the technical problem that the reasoning time of the fault detection based on rule matching in the prior art is long and the vehicle fault detection efficiency is low is solved. At the same time, the present embodiment determines the fault influencing factors according to the target fault information, and when there are environmental factors in the fault influencing factors, determines the fault resolution strategy according to the current environmental information, and performs fault processing on the vehicle according to the fault resolution strategy, thereby ensuring the driving safety of the vehicle.

[0085] refer to Figure 4 , Figure 4 It is a flow chart of the second embodiment of the fault detection method based on rule matching of the present invention.

[0086] Based on the above first embodiment, in order to accurately determine the faulty component in the vehicle and improve the fault detection accuracy of the vehicle, in this embodiment, step S30 includes:

[0087] Step S301: determining an abnormal area of ​​the vehicle according to the sound information and the vibration information.

[0088] It should be noted that the above abnormal area may be an area in the vehicle where a component failure may occur. In practical applications, since abnormal noise or vibration is usually emitted when a component fails, the system can first preliminarily determine the area where the abnormal noise or vibration exists based on the sound information and vibration information in the vehicle, and determine the area as an abnormal area.

[0089] Step S302: extracting target image information corresponding to the abnormal area from the vehicle image information.

[0090] It should be understood that the target image information may be image information of an abnormal area in the vehicle. In this embodiment, in order to accurately identify a faulty component in the abnormal area, the image information of the abnormal area may be extracted from all the image information of the vehicle to obtain the target image information.

[0091] Step S303: determining a target faulty component corresponding to the vehicle based on the target image information.

[0092] In actual applications, if abnormal noise and vibration are found in the area near the vehicle tires based on the vehicle's sound and vibration information, the vehicle tire area can be determined as an abnormal area, and the target image information of the vehicle tire area can be extracted from the vehicle's image information. The system can then further determine whether the vehicle tires are faulty based on the target image information, and then accurately determine the target faulty component of the vehicle.

[0093] Furthermore, the step S303 includes:

[0094] Step S303a: extracting component feature information corresponding to the abnormal area from the target image information.

[0095] It should be understood that the above-mentioned component characteristic information may be characteristic information corresponding to the components in the abnormal area, such as the state corresponding to the components in the abnormal area (such as tire pressure, whether the engine is rotating, etc.), and this embodiment does not limit this.

[0096] Step S303b: Obtain standard component feature information corresponding to all components in the abnormal area.

[0097] It can be understood that the above-mentioned standard component characteristic information may be characteristic information of the component in the abnormal area when no failure occurs.

[0098] Step S303c: Compare the component feature information with the standard component feature information.

[0099] Step S303d: Determine the matching degree between the component feature information and the standard component feature information according to the comparison result.

[0100] It should be noted that the above-mentioned matching degree may be the matching degree between the component feature information and the standard component feature information.

[0101] Step S303e: determining a target faulty component corresponding to the vehicle from the abnormal area according to the matching degree.

[0102] It should be noted that the higher the degree of matching between component feature information and standard component feature information, the higher the similarity between the component feature information and the standard component feature information, that is, the higher the similarity between the current state of the component in the abnormal area and its state before the failure, the lower the possibility of failure of the component; if the lower the degree of matching between the component feature information and the standard component feature information, the lower the similarity between the component feature information and the standard component feature information, that is, the lower the similarity between the current state of the component in the abnormal area and its state before the failure, the higher the possibility of failure of the component.

[0103] In a specific implementation, the system can extract component feature information of all components in the abnormal area from the target image information corresponding to the abnormal area, and extract standard component feature information when the component is not faulty from the image information of all components in the abnormal area stored in the preset vehicle image database, and then compare the component feature information with the standard component feature information, and determine the degree of match between the component feature information and the standard component feature information based on the comparison result, so as to determine the target faulty component corresponding to the vehicle from the abnormal area according to the degree of match. Specifically, if the abnormal area is the area where the tire is located, the air pressure of the tire at this time can be extracted from the target image information, and the air pressure of the tire when it is not faulty can be determined, and the two air pressures can be compared to determine the similarity between the current air pressure of the tire and the normal air pressure, so as to determine whether the vehicle tire is faulty, and then determine the target faulty component of the vehicle.

[0104] This embodiment determines the abnormal area of ​​the vehicle based on the sound information and vibration information of the vehicle, extracts the target image information corresponding to the abnormal area from the vehicle image information, and then determines the target faulty component corresponding to the vehicle based on the target image information, thereby accurately determining the faulty component in the vehicle and improving the vehicle fault detection accuracy.

[0105] refer to Figure 5 , Figure 5 It is a flowchart diagram of the third embodiment of the fault detection method based on rule matching of the present invention.

[0106] Based on the above embodiments, in order to perform accurate rule matching through a rule tree to obtain vehicle fault information so as to improve the accuracy and efficiency of vehicle fault detection, in this embodiment, step S40 includes:

[0107] Step S401: performing semantic recognition on the component information, and extracting the component name and component additional information from the component information.

[0108] It should be noted that the component name may be the name of the target fault component. Correspondingly, the component additional information may be information such as the operating state and fault phenomenon of the target fault component, which is not limited in this embodiment.

[0109] Step S402: searching the rule tree of the rule engine for a target rule tree with the component name as the root node.

[0110] It should be understood that the target rule tree may be a rule tree corresponding to a target faulty component, that is, a rule tree with the component name of the target faulty component as a root node.

[0111] In actual applications, the rule engine stores rule trees corresponding to all components in the vehicle. These rule trees are built with the component name corresponding to each component as the root node, the operating state corresponding to each component and the possible fault phenomenon in the operating state as the child nodes, and the leaf nodes can be the fault information corresponding to the fault phenomenon in the corresponding operating state. Therefore, in order to accurately detect faults in the vehicle, after determining the target fault component of the vehicle, the component name corresponding to the target fault component is matched from all rule trees in the rule engine to obtain the target rule tree with the component name of the target fault component as the root node, so as to determine the fault information of the vehicle according to the target rule tree.

[0112] Step S403: Match the component additional information with the target rule tree to determine target fault information corresponding to the vehicle.

[0113] It should be noted that after determining the target rule tree, the operating status and fault phenomenon corresponding to the target faulty component can be matched one by one with the sub-nodes in the target rule tree to determine the target fault information corresponding to the vehicle.

[0114] Furthermore, the step S403 includes:

[0115] Step S403a: Determine the component operating state and target fault phenomenon corresponding to the target faulty component according to the component additional information.

[0116] It should be understood that the above-mentioned component operating state may be the current operating state of the target faulty component; correspondingly, the above-mentioned target fault phenomenon may be the fault phenomenon currently exhibited by the target faulty component.

[0117] Step S403b: sequentially matching the component operation status and the target fault phenomenon with the first subnode and the second subnode in the target rule tree.

[0118] It can be understood that the first sub-node can be a sub-node directly connected to the root node in the target rule tree; the second sub-node can be a sub-node directly connected to the first sub-node in the target rule tree. Figure 3 As shown, Figure 3 In the example, “operating status 1” and “operating status 2” are the first sub-nodes, and “fault phenomenon 1”, “fault phenomenon 2”, “fault phenomenon 3” and “fault phenomenon 4” are the second sub-nodes.

[0119] Step S403c: Determine the target fault information corresponding to the vehicle according to the matching result.

[0120] In practical applications, the component operation state and target fault phenomenon corresponding to the target fault component are determined, and the component operation state and the target fault phenomenon are matched with the first sub-node and the second sub-node in the target rule tree in sequence, so that the corresponding target fault information can be obtained when the match is successful. Specifically, the component operation state of the target fault component can be matched with the first sub-node in the target rule tree first. If the match is successful, the target fault phenomenon of the target fault component can be further matched with the second sub-node under the first sub-node. If the match is successful, the fault information corresponding to the successfully matched fault phenomenon can be determined as the target fault information.

[0121] Furthermore, in order to further improve the accuracy of the acquired fault information, the step S403c includes: obtaining the phenomenon weight information corresponding to the target fault phenomenon; determining the fault category corresponding to the target fault component based on the matching result and the phenomenon weight information; determining the fault cause corresponding to the fault category, and determining the target fault information corresponding to the vehicle based on the fault cause.

[0122] It should be noted that the above phenomenon weight information may be the weight corresponding to the fault phenomenon.

[0123] In actual applications, the component operating status and target fault phenomenon corresponding to the target faulty component may successfully match multiple nodes in the target rule tree, that is, there may be multiple target fault phenomena. Therefore, the system can determine the phenomenon weights corresponding to all target fault phenomena to filter out target fault phenomena with lower weights, and then determine the fault category corresponding to the target faulty component based on the remaining target fault phenomena, so that the fault cause corresponding to the fault category can be determined as the target fault information corresponding to the vehicle.

[0124] This embodiment performs semantic recognition on the component information of the target faulty component, extracts the component name and component additional information in the component information, searches for a target rule tree with the component name as the root node from the rule tree in the rule engine, and matches the component additional information with the target rule tree to determine the target fault information corresponding to the vehicle, so that accurate rule matching can be performed through the rule tree to obtain the vehicle's fault information, thereby improving the accuracy and efficiency of vehicle fault detection.

[0125] In addition, an embodiment of the present invention further proposes a storage medium on which a rule-matching-based fault detection program is stored. When the rule-matching-based fault detection program is executed by a processor, the steps of the rule-matching-based fault detection method described above are implemented.

[0126] Reference Figure 6 , Figure 6 It is a structural block diagram of the first embodiment of the fault detection device based on rule matching of the present invention.

[0127] like Figure 6 As shown, the fault detection device based on rule matching proposed in the embodiment of the present invention includes:

[0128] The information acquisition module 601 is used to acquire the sound information and vibration information corresponding to the vehicle when a fault signal of the vehicle is detected;

[0129] The information acquisition module 601 is further used to acquire vehicle image information of the vehicle from a preset vehicle image database, wherein the preset vehicle image database stores a global image of the vehicle collected in real time;

[0130] A fault component determination module 602 is used to determine a target fault component corresponding to the vehicle based on the sound information, the vibration information and the vehicle image information;

[0131] The fault detection module 603 is used to determine the component information of the target faulty component, and determine the target fault information corresponding to the vehicle based on the component information and the rule tree matching in the rule engine.

[0132] Furthermore, the fault detection module 603 is also used to determine the fault influencing factors according to the target fault information; determine whether the fault influencing factors include environmental factors; if so, obtain the current environmental information and determine the fault resolution strategy according to the current environmental information; and perform fault processing on the vehicle according to the fault resolution strategy.

[0133] The fault detection device based on rule matching of the present embodiment discloses that when a fault signal of a vehicle is detected, the sound information and vibration information corresponding to the vehicle are obtained; the vehicle image information of the vehicle is obtained from a preset vehicle image database, and the preset vehicle image database stores a global image of the vehicle collected in real time; the target fault component corresponding to the vehicle is determined based on the sound information, vibration information and vehicle image information; the component information of the target fault component is determined, and the target fault information corresponding to the vehicle is determined based on the component information and the rule tree matching in the rule engine; compared with the prior art that matches the fault-related data of the vehicle with the fault rules pre-established in the vehicle system to realize the fault detection of the vehicle, since the present embodiment determines the target fault component of the vehicle based on the sound information, vibration information and vehicle image information of the vehicle, and determines the target fault information of the vehicle based on the fault information of the target fault component and the rule tree matching in the rule engine, the technical problem that the reasoning time of the fault detection based on rule matching in the prior art is long and the vehicle fault detection efficiency is low is solved. At the same time, the present embodiment determines the fault influencing factors according to the target fault information, and when there are environmental factors in the fault influencing factors, determines the fault resolution strategy according to the current environmental information, and performs fault processing on the vehicle according to the fault resolution strategy, thereby ensuring the driving safety of the vehicle.

[0134] Based on the first embodiment of the fault detection device based on rule matching of the present invention, a second embodiment of the fault detection device based on rule matching of the present invention is proposed.

[0135] In this embodiment, the faulty component determination module 602 is also used to determine the abnormal area of ​​the vehicle based on the sound information and the vibration information; extract the target image information corresponding to the abnormal area from the vehicle image information; and determine the target faulty component corresponding to the vehicle based on the target image information.

[0136] Furthermore, the faulty component determination module 602 is also used to extract component feature information corresponding to the abnormal area from the target image information; obtain standard component feature information corresponding to all components in the abnormal area; compare the component feature information with the standard component feature information; determine the degree of matching between the component feature information and the standard component feature information based on the comparison result; and determine the target faulty component corresponding to the vehicle from the abnormal area based on the matching degree.

[0137] This embodiment determines the abnormal area of ​​the vehicle based on the sound information and vibration information of the vehicle, extracts the target image information corresponding to the abnormal area from the vehicle image information, and then determines the target faulty component corresponding to the vehicle based on the target image information, thereby accurately determining the faulty component in the vehicle and improving the vehicle's fault detection accuracy.

[0138] Based on the above-mentioned device embodiments, a third embodiment of a fault detection device based on rule matching of the present invention is proposed.

[0139] In this embodiment, the fault detection module 603 is also used to perform semantic recognition on the component information, extract the component name and component additional information in the component information; search for a target rule tree with the component name as the root node from the rule tree of the rule engine; and match the component additional information with the target rule tree to determine the target fault information corresponding to the vehicle.

[0140] Furthermore, the fault detection module 603 is also used to determine the component operating state and target fault phenomenon corresponding to the target faulty component based on the component additional information; match the component operating state and the target fault phenomenon with the first subnode and the second subnode in the target rule tree in turn; and determine the target fault information corresponding to the vehicle based on the matching result.

[0141] Furthermore, the fault detection module 603 is also used to obtain phenomenon weight information corresponding to the target fault phenomenon; determine the fault category corresponding to the target fault component according to the matching result and the phenomenon weight information; determine the fault cause corresponding to the fault category, and determine the target fault information corresponding to the vehicle according to the fault cause.

[0142] This embodiment performs semantic recognition on the component information of the target faulty component, extracts the component name and component additional information in the component information, searches for a target rule tree with the component name as the root node from the rule tree in the rule engine, and matches the component additional information with the target rule tree to determine the target fault information corresponding to the vehicle, so that accurate rule matching can be performed through the rule tree to obtain the vehicle's fault information, thereby improving the accuracy and efficiency of vehicle fault detection.

[0143] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0144] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0145] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0146] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A fault detection method based on rule matching, characterized in that: The fault detection method based on rule matching includes: When a fault signal of a vehicle is detected, obtaining sound information and vibration information corresponding to the vehicle; Acquiring vehicle image information of the vehicle from a preset vehicle image database, wherein the preset vehicle image database stores a global image of the vehicle collected in real time; determining a target faulty component corresponding to the vehicle based on the sound information, the vibration information and the vehicle image information; Component information of the target fault component is determined, and target fault information corresponding to the vehicle is determined based on the component information and a rule tree match in a rule engine.

2. The fault detection method based on rule matching according to claim 1, characterized in that: The step of determining a target faulty component corresponding to the vehicle based on the sound information, the vibration information and the vehicle image information comprises: determining an abnormal area of ​​the vehicle according to the sound information and the vibration information; Extracting target image information corresponding to the abnormal area from the vehicle image information; A target faulty component corresponding to the vehicle is determined based on the target image information.

3. The fault detection method based on rule matching according to claim 2, characterized in that: The step of determining a target faulty component corresponding to the vehicle based on the target image information comprises: Extracting component feature information corresponding to the abnormal area from the target image information; Acquire standard component feature information corresponding to all components in the abnormal area; comparing the component characteristic information with the standard component characteristic information; Determining the matching degree between the component feature information and the standard component feature information according to the comparison result; A target faulty component corresponding to the vehicle is determined from the abnormal area according to the matching degree.

4. The fault detection method based on rule matching according to claim 1, characterized in that: The step of determining target fault information corresponding to the vehicle based on the component information and rule tree matching in the rule engine includes: Performing semantic recognition on the component information to extract component names and component additional information from the component information; Searching for a target rule tree with the component name as a root node from a rule tree of a rule engine; The component additional information is matched with the target rule tree to determine target fault information corresponding to the vehicle.

5. The fault detection method based on rule matching according to claim 4, characterized in that: The step of matching the component additional information with the target rule tree to determine the target fault information corresponding to the vehicle includes: Determine the component operation state and target fault phenomenon corresponding to the target faulty component according to the component additional information; Sequentially matching the component operation state and the target fault phenomenon with the first subnode and the second subnode in the target rule tree; The target fault information corresponding to the vehicle is determined according to the matching result.

6. The fault detection method based on rule matching according to claim 5, characterized in that: The step of determining target fault information corresponding to the vehicle according to the matching result includes: Obtaining phenomenon weight information corresponding to the target fault phenomenon; Determine the fault category corresponding to the target faulty component according to the matching result and the phenomenon weight information; Determine a fault cause corresponding to the fault category, and determine target fault information corresponding to the vehicle according to the fault cause.

7. The fault detection method based on rule matching according to claim 1, characterized in that: After the step of determining the target fault information corresponding to the vehicle based on the component information and the rule tree matching in the rule engine, the method further includes: Determining a fault influencing factor according to the target fault information; Determine whether the fault influencing factor is an environmental factor; If so, obtain the current environment information and determine the fault resolution strategy based on the current environment information; Fault resolution is performed on the vehicle according to the fault resolution strategy.

8. A fault detection device based on rule matching, characterized in that: The device comprises: An information acquisition module, used to acquire sound information and vibration information corresponding to the vehicle when a fault signal of the vehicle is detected; The information acquisition module is further used to acquire vehicle image information of the vehicle from a preset vehicle image database, wherein the preset vehicle image database stores a global image of the vehicle collected in real time; a faulty component determination module, configured to determine a target faulty component corresponding to the vehicle based on the sound information, the vibration information and the vehicle image information; A fault detection module is used to determine component information of the target faulty component, and determine target fault information corresponding to the vehicle based on the component information and rule tree matching in a rule engine.

9. A fault detection device based on rule matching, characterized in that: The device comprises: a memory, a processor, and a rule-matching-based fault detection program stored in the memory and executable on the processor, wherein the rule-matching-based fault detection program is configured to implement the steps of the rule-matching-based fault detection method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a rule-matching-based fault detection program, which, when executed by a processor, implements the steps of the rule-matching-based fault detection method according to any one of claims 1 to 7.

Images